© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42202
    Prev
    Next
    INDEX
    Explanations

    preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.86
     متعلقه
    -0.65
     ControllerBase
    -0.63
     EconPapers
    -0.63
    makeConstraints
    -0.61
    exitRule
    -0.59
    ///</
    -0.59
    phrine
    -0.58
     {}'.
    -0.58
    ValueStyle
    -0.57
    POSITIVE LOGITS
    èlement
    0.47
     lois
    0.46
     referenties
    0.46
    etted
    0.45
    cionais
    0.45
    MERCE
    0.45
    ticon
    0.44
    ement
    0.44
    kuuta
    0.44
     stanovnika
    0.43
    Activations Density 0.011%

    No Known Activations